On the impact of up-sampling method for super-resolution image reconstruction

Jong Hyun Park, Moon Gi Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In constrained least squares based super-resolution image reconstruction, it is an important issue to up-sample and merge the high-frequency information contained in low resolution images efficiently and without artifact. In this paper, we analyze up-sampling methods used for registering low resolution data to high resolution grid and show their advantages and disadvantages. In addition, we propose a new up-sampling and merging method called "Hybrid up-sampling". The proposed method accurately incorporates the high frequency data in low resolution images and minimizes the artifact caused by data deficiency. By this method, regions that the registered high frequency data do not cover are naturally regularized without using complex regularizes. Experimental results show that the choice of up-sampler significantly affects the quality of resulting images and the proposed up-sampler gives better results compared to conventional simple up-samplers, especially when the number of low resolution images is deficient.

Original languageEnglish
Title of host publicationProceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008
Pages208-212
Number of pages5
Publication statusPublished - 2008 Dec 1
Event10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008 - Innsbruck, Austria
Duration: 2008 Feb 132008 Feb 15

Publication series

NameProceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008

Other

Other10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008
CountryAustria
CityInnsbruck
Period08/2/1308/2/15

Fingerprint

Image resolution
Image reconstruction
Sampling
Merging

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Park, J. H., & Kang, M. G. (2008). On the impact of up-sampling method for super-resolution image reconstruction. In Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008 (pp. 208-212). (Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008).
Park, Jong Hyun ; Kang, Moon Gi. / On the impact of up-sampling method for super-resolution image reconstruction. Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008. 2008. pp. 208-212 (Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008).
@inproceedings{b71a5b15bd894f65b12df2e4bbfaaabc,
title = "On the impact of up-sampling method for super-resolution image reconstruction",
abstract = "In constrained least squares based super-resolution image reconstruction, it is an important issue to up-sample and merge the high-frequency information contained in low resolution images efficiently and without artifact. In this paper, we analyze up-sampling methods used for registering low resolution data to high resolution grid and show their advantages and disadvantages. In addition, we propose a new up-sampling and merging method called {"}Hybrid up-sampling{"}. The proposed method accurately incorporates the high frequency data in low resolution images and minimizes the artifact caused by data deficiency. By this method, regions that the registered high frequency data do not cover are naturally regularized without using complex regularizes. Experimental results show that the choice of up-sampler significantly affects the quality of resulting images and the proposed up-sampler gives better results compared to conventional simple up-samplers, especially when the number of low resolution images is deficient.",
author = "Park, {Jong Hyun} and Kang, {Moon Gi}",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9780889867192",
series = "Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008",
pages = "208--212",
booktitle = "Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008",

}

Park, JH & Kang, MG 2008, On the impact of up-sampling method for super-resolution image reconstruction. in Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008. Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008, pp. 208-212, 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008, Innsbruck, Austria, 08/2/13.

On the impact of up-sampling method for super-resolution image reconstruction. / Park, Jong Hyun; Kang, Moon Gi.

Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008. 2008. p. 208-212 (Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - On the impact of up-sampling method for super-resolution image reconstruction

AU - Park, Jong Hyun

AU - Kang, Moon Gi

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In constrained least squares based super-resolution image reconstruction, it is an important issue to up-sample and merge the high-frequency information contained in low resolution images efficiently and without artifact. In this paper, we analyze up-sampling methods used for registering low resolution data to high resolution grid and show their advantages and disadvantages. In addition, we propose a new up-sampling and merging method called "Hybrid up-sampling". The proposed method accurately incorporates the high frequency data in low resolution images and minimizes the artifact caused by data deficiency. By this method, regions that the registered high frequency data do not cover are naturally regularized without using complex regularizes. Experimental results show that the choice of up-sampler significantly affects the quality of resulting images and the proposed up-sampler gives better results compared to conventional simple up-samplers, especially when the number of low resolution images is deficient.

AB - In constrained least squares based super-resolution image reconstruction, it is an important issue to up-sample and merge the high-frequency information contained in low resolution images efficiently and without artifact. In this paper, we analyze up-sampling methods used for registering low resolution data to high resolution grid and show their advantages and disadvantages. In addition, we propose a new up-sampling and merging method called "Hybrid up-sampling". The proposed method accurately incorporates the high frequency data in low resolution images and minimizes the artifact caused by data deficiency. By this method, regions that the registered high frequency data do not cover are naturally regularized without using complex regularizes. Experimental results show that the choice of up-sampler significantly affects the quality of resulting images and the proposed up-sampler gives better results compared to conventional simple up-samplers, especially when the number of low resolution images is deficient.

UR - http://www.scopus.com/inward/record.url?scp=62949193721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62949193721&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:62949193721

SN - 9780889867192

T3 - Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008

SP - 208

EP - 212

BT - Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008

ER -

Park JH, Kang MG. On the impact of up-sampling method for super-resolution image reconstruction. In Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008. 2008. p. 208-212. (Proceedings of the 10th IASTED International Conference on Computer Graphics and Imaging, CGIM 2008).